Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b Conversational Qwen3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Menlo/Jan-nano
Jan Nano Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Jan Nano Parameters and Internals
| LLM Name | Jan Nano |
| Repository 🤗 | https://huggingface.co/Menlo/Jan-nano |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 8.1 GB |
| Updated | 2025-06-17 |
| Maintainer | Menlo |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Jan Nano
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 Embedding 4B | 40K / 8.1 GB | 29917 | 64 |
| Qwen3 Reranker 4B | 40K / 8.1 GB | 8604 | 55 |
| Qwen3 4B FP8 | 40K / 5.2 GB | 36238 | 22 |
| Qwen3 4B | 40K / 8.1 GB | 17594 | 7 |
| Chinda Qwen3 4B | 40K / 8.1 GB | 280 | 10 |
| Qwen3 4B Esper3 | 40K / 16.1 GB | 1509 | 8 |
| Qwen3 4B Abliterated | 40K / 8.1 GB | 1454 | 13 |
| ...iefied Qwen3 4B Abliterated V1 | 40K / 8.1 GB | 1299 | 10 |
| Bootes Qwen3 Coder Reasoning | 40K / 8.1 GB | 1237 | 2 |
| Lacaille MoT 4B Supreme2 | 40K / 8.1 GB | 77 | 2 |
Rank the Jan Nano Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 48225 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124